Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 256 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.7827. Min Act: -0.1700

Data Index: 2448148 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.6766. Min Act: -0.1700

Data Index: 1685565 (Open Web Text)

Max Activating Token Index: 888

Text #2

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.5094. Min Act: -0.1700

Data Index: 7297492 (Open Web Text)

Max Activating Token Index: 910

Text #3

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.4955. Min Act: -0.1700

Data Index: 2849584 (Open Web Text)

Max Activating Token Index: 836

Text #4

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.4688. Min Act: -0.1700

Data Index: 556842 (Open Web Text)

Max Activating Token Index: 448

Text #5

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.4545. Min Act: -0.1700

Data Index: 6178842 (Open Web Text)

Max Activating Token Index: 170

Text #6

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.4368. Min Act: -0.1700

Data Index: 7748242 (Open Web Text)

Max Activating Token Index: 1010

Text #7

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.4285. Min Act: -0.1700

Data Index: 5718986 (Open Web Text)

Max Activating Token Index: 238

Text #8

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.4163. Min Act: -0.1700

Data Index: 4488529 (Open Web Text)

Max Activating Token Index: 1015

Text #9

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3976. Min Act: -0.1700

Data Index: 3597953 (Open Web Text)

Max Activating Token Index: 921

Text #10

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3957. Min Act: -0.1700

Data Index: 910876 (Open Web Text)

Max Activating Token Index: 823

Text #11

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3921. Min Act: -0.1700

Data Index: 773434 (Open Web Text)

Max Activating Token Index: 566

Text #12

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.4050. Min Act: -0.1700

Data Index: 1517806 (Open Web Text)

Max Activating Token Index: 496

Text #13

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3971. Min Act: -0.1700

Data Index: 4532204 (Open Web Text)

Max Activating Token Index: 358

Text #14

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3665. Min Act: -0.1700

Data Index: 759247 (Open Web Text)

Max Activating Token Index: 365

Text #15

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3667. Min Act: -0.1700

Data Index: 1111290 (Open Web Text)

Max Activating Token Index: 859

Text #16

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3620. Min Act: -0.1700

Data Index: 2996347 (Open Web Text)

Max Activating Token Index: 479

Text #17

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3640. Min Act: -0.1700

Data Index: 2808073 (Open Web Text)

Max Activating Token Index: 856

Text #18

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3792. Min Act: -0.1700

Data Index: 4363060 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 4.7827. Min Range: -4.7827

Max Act: 4.3848. Min Act: -0.1700

Data Index: 5337361 (Open Web Text)

Max Activating Token Index: 388